Compound Poisson Regression Models

  • John Hinde
Part of the Lecture Notes in Statistics book series (LNS, volume 14)


Count data are easily modelled in GLIM using the Poisson distribution. However, in modelling such data the counts are often aggregated over one or more factors, or important explanatory variables are unavailable and as a result the fit obtained is often poor. This paper examines a method of allowing for this unexplained variation by introducing an independent random variable into the linear model for the Poisson mean, giving a compound Poisson model for the observed data. By assuming a known form for the distribution of this random variable, in particular the normal distribution, and using a combination of numerical integration, the EM algorithm and iteratively reweighted least squares, maximum likelihood estimates can be obtained for the parameters. Macros for implementing this technique are presented and its use is illustrated with several examples.


Count Data Poisson Distribution Over-Dispersion Compound Poisson Maximum Likelihood Numerical Integration Em Algorithm IRLS 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Aitkin, M.A. (1978). The analysis of unbalanced cross-classifications (with discussion). J.R. Statist.Soc. A, 141, 195–223.MathSciNetMATHCrossRefGoogle Scholar
  2. Dempster, A.P., Laird, N.M. and Rubin, D.B. (1977). Maximum likelihood from incomplete data via the EM algorithm (with discussion). J.R. Statist. Soc.B, 39, 1–38.MathSciNetMATHGoogle Scholar
  3. Frome, E.L., Kutner, M.H. and Beauchamp, J.J. (1973). Regression analysis of Poisson-distributed data. J.Amer.Statist. Assoc, 68, 935–940.MathSciNetMATHCrossRefGoogle Scholar
  4. Gilchrist, R. (1981). Calculation of residuals for all GLIM models. GLIM Newsletter, 4, 26–28.Google Scholar
  5. Haberman, S.J. (1974). The analysis of frequency data. University of Chicago Press.MATHGoogle Scholar
  6. Neider, J.A. and Wedderburn, R.W.M. (1972). Generalized linear models. J.R.Statist. Soc. A, 135, 370–384.CrossRefGoogle Scholar
  7. Pocock, S.J., Cook, D.G. and Beresford, S.A.A. (1981). Regression of area mortality rates on explanatory variables: What weighting is appropriate? Appl. Statist, 30, 286–296.MATHCrossRefGoogle Scholar
  8. Stroud, A.H. and Sechrest, D. (1966). Gaussian quadrature formulas. Englewood Cliffs (N.J.): Prentice Hall.MATHGoogle Scholar

Copyright information

© Springer-Verlag New York Inc. 1982

Authors and Affiliations

  • John Hinde
    • 1
  1. 1.Centre for Applied StatisticsUniversity of LancasterUK

Personalised recommendations